Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|---|---|---|---|---|---|---|---|
| 1 | Muse Spark 1.3 | 0.0996 | $565.41 | 641.8M | 1.1M | 19h 58m | 1422 | 16 |
| 2 | Muse Spark 1.3 | 0.0752 | $635.38 | 703.6M | 636k | 19h 52m | 1342 | 3 |
| 3 | Muse Spark 1.3 | 0.0491 | $376.25 | 2119.7M | 1.7M | 19h 47m | 4639 | 144 |
| 4 | Muse Spark 1.3 | 0.0092 | $609.32 | 704.0M | 1.1M | 19h 57m | 1497 | 2 |
| 5 | Muse Spark 1.3 | 0.0000 | $571.21 | 716.3M | 974k | 19h 59m | 1683 | 2 |